https://github.com/cran/meta
Tip revision: 91d07f94f7aef8050ca5d4a3099100d7f2d886d3 authored by Guido Schwarzer on 20 June 2013, 00:00:00 UTC
version 2.4-1
version 2.4-1
Tip revision: 91d07f9
NEWS
2013-06-20, version 2.4-1
Functions metaprop:
- bug fix so that call of forest.meta function with metaprop object
does not result in an error message (bug was introduced with meta,
version 2.4-0)
- new list components incr, allincr, addincr added to metaprop R
object (should have been part of exported list since meta version
1.5-0)
Functions print.meta:
- new arguments prediction and level.predict to print prediction
interval for a new study
Functions print.summary.meta:
- call of internal function asin2p using argument warn to only print
warnings if result for fixed effect, random effects model or
prediction interval are printed
Functions forest.meta:
- call of internal function asin2p using argument warn to only print
warnings if result for fixed effect, random effects model or
prediction interval are plotted
Function asin2p (used internally for metaprop objects):
- new argument warn to only print a warning in certain situations
(see comments on functions print.meta and forest.meta)
Help pages metabin, metacont, metacor, metacr, metagen, metaprop:
- Example to generate forest plot added
2013-06-17, version 2.4-0
Functions metagen, metabin, metacont, metaprop, metacor:
- new arguments prediction and level.predict
(prediction interval for a new study)
- new argument tau.common (common tau-squared across subgroups)
- help pages updated accordingly
Function metaprop:
- new default summary measure (sm="PLOGIT")
- argument freeman.tukey removed
Function summary.meta:
- new arguments prediction and level.predict
(prediction interval for a new study)
- new list component tau.common considered internally (for objects of
type metagen, metabin, metacont, metaprop, metacor)
- modified such that correct values for list components incr, allincr,
and addincr of metaprop object are considered in calculations
Function forest.meta:
- modified such that prediction interval can be plotted
(new arguments: prediction, level.predict, text.predict,
col.predict, col.predict.lines, fs.predict, fs.predict.labels,
ff.predict, ff.predict.labels)
- modified such that correct values for list components incr, allincr,
and addincr of metaprop object are considered in calculations
- modified such that information on confidence limits is printed for
pooled estimates if CI level is different from CI level for
individual studies
Function print.summary.meta:
- modified such that a prediction interval is printed if argument
prediction is TRUE
- new list component tau.common considered internally (for objects of
type metagen, metabin, metacont, metaprop, metacor)
Function catmeth (only used internally):
- print information if common tau-squared assumed across
subgroups (argument tau.common)
2013-05-12, version 2.3-0
Function forest.meta:
- modified such that fixed effect and random effects estimates and
confidence intervals are only (re)calculated for very old versions of
R package meta (version number < 2.x-x)
Functions metabin:
- bug fix so that function call with arguments sm="RR" and
allstudies=TRUE does not result in an error message in meta-analyses
with zero events in both groups
2013-03-20, version 2.2-1
Function forest.meta:
- new argument lab.NA (default: lab.NA=".") to label NAs (in older
version of R package meta the fixed label 'NA' was used)
- modified such that arguments colgap.forest.left and
colgap.forest.right are considered (instead of only colgap.forest)
Functions labbe.metabin and labbe.default:
- bug fix so that function call does not result in an error message if
any event probability is equal to NA
Function format.p (only used internally):
- bug fix so that function call does not result in an error message if
any NAs were provided in the first function argument
2013-03-12, version 2.2-0
Function metabin:
- modified so that studies with all events in both groups will be
included in meta-analysis by default (in older versions of R package
meta these studies were only included if argument allstudies=TRUE)
- modified so that the standard error is positive for studies with all
events in both groups
(see Hartung & Knapp (2001), Stat Med, equation (18))
Function forest.meta:
- modified so that values provided by argument xlim will be printed on
x-axis label for relative effect measures (i.e. argument sm is equal
to "RR", "OR", or "HR")
- internally calculated default values for arguments smlab.pos and
xlab.pos changed such that they will always lie withing plotting
range
2012-11-29, version 2.1-4
Functions forest.meta, metacum, metainf and print.meta:
- modified so that backtransformation of Freeman-Tukey Double arcsine
transformation (argument sm='PFT' in function metaprop) is
calculated correctly for objects of class 'metacum' and 'metainf'
Function asin2p:
- modified so that values outside the admissible range are set to the
boundary values (i.e. results in estimated probabilities of 0 or 1).
A warning is printed in this case.
Help pages metacum and metainf:
- new argument n.harmonic.mean documented
2012-11-20, version 2.1-3
Function forest.meta:
- modified so that the function works for an object of class
'metacum' or 'metainf' and argument sm equal to 'PFT' which
previously resulted in an error message
'Error in if (col$range[1] <= TE.fixed & TE.fixed <= col$range[2]) ...'
2012-10-25, version 2.1-2
Functions forest.meta, metacum, metainf, summary.meta:
- modified so that the function works if argument 'method.tau' is
different from the default which previously resulted in an error
message
'Error in sqrt(W) %*% X : non-conformable arguments'
Function forest.meta:
- argument 'byvar' uses corresponding list element from
meta-analysis object as default
2012-08-12, version 2.1-1
Function summary.meta:
- list element 'k0' added to returned object for trim-and-fill method
Function print.summary.meta:
- print number of added studies for trim-and-fill method
2012-05-18, version 2.1-0
Functions trimfill.meta and trimfill.default:
- arguments hakn and method.tau added
Functions metacum and metainf:
- modified so that class 'trimfill' is added to object if function
metacum or metainf is used on object of class 'trimfill'
Function catmeth, print.meta, print.summary.meta:
- modified so that information on use of trim-and-fill method is
printed
Functions metabias.meta:
- modified so that error message is printed if used with object of
class 'metacum' or 'metainf'
Functions funnel.meta:
- modified so that error message is printed if used with object of
class 'metacum' or 'metainf'
- modified so that by default different plot symbols (argument pch)
are used with object of class 'trimfill'
Function .onLoad:
- modified so that version nummer of meta package is printed when
library is loaded
Help pages trimfill.meta and trimfill.default:
- arguments hakn and method.tau documented
Help page funnel.meta:
- changed default for argument pch documented
2012-05-03, version 2.0-4
Function metaprop:
- modified so that variance estimate for log- and logit-transformation
(sm="PLN" and sm="PLOGIT") is based on Pettigrew et al. (1986).
Reference Pettigrew et al. (1986) has been added to the following help
pages:
- metabin, metaprop
2012-04-17, version 2.0-2
Function metaprop:
- modified so that a warning is printed if any sample size
(argument n) is smaller than 10 for Freeman-Tukey-Transformation,
i.e. sm="PFT"
2012-04-04, version 2.0-1
Functions metabin, metacont, metacor, metagen, metaprop:
- modified so that these functions can be used with arguments subset
and byvar of different length
2012-03-20, version 2.0-0
Major revision
R package meta linked to R package metafor to provide additional
statistical methods, e.g. meta-regression and other estimates for
tau-squared (REML, ...)
New functions:
- metareg (meta-regression)
- metabias (generic method for function metabias)
- metabias.default (generic method for function metabias)
- metabias.meta (generic method for function metabias)
- metabias.rm5 (generic method for function metabias)
- print.rm5 (generic method for rm5-object)
- print.summary.rm5 (generic method for rm5-object)
- summary.rm5 (generic method for rm5-object)
- catmeth (function used internally)
- crtitle (function used internally)
- hypergeometric (function used internally)
- is.installed.metafor (function used internally)
- kentau (function used internally)
- linregcore (function used internally)
- p2logit (function used internally)
Functions metabin, metacont, metacor, metagen, metaprop:
- new arguments:
- hakn (Hartung-Knapp method)
- method.tau (estimation method for tau-squared)
- tau.preset (fixed value for tau)
- TE.tau (prespecified treatment effect to estimate tau)
- method.bias (test for funnel plot asymmetry used in metabias)
- label.left (Label on left side of forest plot, new argument in
functions metabin, metacont, and metagen)
- label.right (Label on right side of forest plot, new argument in
functions metabin, metacont, and metagen)
- warn (print warning messages, new argument in functions metacont
and metagen)
- new list components of returned object:
- se.tau2 (standard error of tau-squared)
- hakn (Hartung-Knapp method)
- method.tau (estimation method for tau-squared)
- tau.preset (fixed value for tau)
- TE.tau (prespecified treatment effect to estimate tau)
- method.bias (test for funnel plot asymmetry used in metabias)
- label.left (Label on left side of forst plot, new list component
in functions metabin, metacont, and metagen)
- label.right (Label on right side of forst plot, new list component
in functions metabin, metacont, and metagen)
- argument 'warn' suppresses more warning messages if FALSE
- function metabin: studies are excluded from meta-analysis if
(event.e > n.e | event.c > n.c) or (n.e <= 0 | n.c <= 0) or
(event.e < 0 | event.c < 0)
Function metacum and metainf:
- modified so that NULL is returned if function is used with a single
study
- modified so that new arguments hakn, method.tau, tau.preset,
method.bias, label.left, label.right are considered in execution of
the function
- argument level removed
Function metaprop:
- modified so that the correct variance function 1/(n+0.5) instead of
1/(n+1) is used for the Freeman-Tukey-Transformation (i.e. sm="PFT")
- see also news on function asin2p
Function asin2p:
- completely rewritten as back transformation of Freeman-Tukey
transformed proportions was inaccurate
- back transformation of Freeman-Tukey proportions according to
Miller (1978) - see help page of R command metaprop
Function print.metabias:
- print a warning if number of studies is too small to conduct a
test for funnel plot asymmetry (see new argument k.min)
Function print.summary.meta:
- new argument bylab.nchar
- print test for subgroup differences for both fixed effect and
random effects model
- value 'invisible(NULL)' returned for metacum and metainf objects
Function metacr:
- new arguments:
- sm (summary measure)
- method (pooling method)
- comb.fixed (fixed effect model)
- comb.random (random effects model)
- swap.events (only for binary data)
- method.tau (estimation method for between-study variance)
- hakn (Hartung-Knapp adjustment)
- title (Title of Cochrane review)
- complab (Comparison label)
- outclab (Outcome label)
- warn (print warning messages)
- removed argument:
- smother (summary measure)
- value 'NULL' returned if no data is available for selection of
comp.no and outcome.no
Function read.rm5:
- changed substantially for reading of RevMan 5.1 files
Function summary.meta:
- modified so that new arguments hakn, method.tau, tau.preset,
method.bias are considered in execution of the function
- argument 'warn' suppresses more warning messages
Function forest.meta:
- modified so that the treatment effect and 95% confidence interval
is printed in the correct order for objects of class metaprop if
argument sort or order is used
- symmetric forest plot by default (argument xlim="s")
- new arguments:
- smlab, smlab.pos, fs.smlab, fflab
(Label for summary measure - at top of figure)
- label.right, label.left, fs.lr, ff.lr
(Label on right and left side)
- overall.hetstat (heterogeneity information for overall effect)
Function funnel.default and funnel.meta:
- modified so that arguments col.fixed and col.random are recognised
Function metabias.default and metabias.meta:
- new argument k.min:
test for funnel plot asymmetry only conducted if number of studies
in meta-analysis is larger or equal to k.min
- new argument '...' (ignored at the moment)
Function trimfill.default and trimfill.meta:
- value 'invisible(NULL)' returned if number of studies is smaller
than 3
New datasets: amlodipine, cisapride
File FLEISS93.MTV moved from directory data to directory extdata
Update of several help pages. Some new help pages added.
2010-10-28, version 1.6-1
Function forest.meta:
- modified so that the number of events is printed in the
correct order for objects of class metaprop if argument
sort or order is used
- modified so that transformed proportions are printed
for individual studies in column 'TE' if function metagen
is used with argument sm equal to either 'PLN', 'PLOGIT',
'PAS', or 'PFT'
Function as.data.frame.meta:
- modified so that the function works for meta-analyses
with six studies which previously resulted in an error message
'Error: evaluation nested too deeply: infinite recursion ...'
- modified so that additional arguments '...' can be passed to
function
Function addvar:
- option stringsAsFactors=FALSE added to internal call of
R function as.data.frame.meta
- additional checks for existence of columns by.x and by.y
- additional checks for situations with duplicate entries
for columns by.x and by.y added
Function print.meta:
- modified so that backtransformed proportions are printed
for individual studies if function metagen is used with
argument sm equal to either 'PLN', 'PLOGIT', 'PAS', or 'PFT'
Examples given in the following help pages have been (slightly)
updated:
- read.mtv, read.rm5, metacr
2010-06-21, version 1.6-0
Function forest.meta:
- for subgroup analyses (i.e. groups defined by argument 'byvar'),
result for both fixed effect and random effects model are printed
(in older versions of the meta package only results for either
fixed effect or random effects model could be printed)
- new arguments text.fixed.w and text.random.w to specify label for
estimates within subgroups
- new arguments to change colour of several parts of the plot:
col.i.inside.square, col.square, col.square.lines,
col.diamond, col.diamond.fixed, col.diamond.random,
col.diamond.lines, col.diamond.fixed.lines, col.diamond.random.lines
- new arguments to print information on heterogeneity measures:
print.I2, print.tau2, print.Q, print.pval.Q,
hetstat, hetlab
- new arguments to change fontsize and fontface of several parts
of the plot:
fs.heading, fs.fixed, fs.random, fs.study,
fs.fixed.labels, fs.random.labels, fs.study.labels,
fs.hetstat, fs.axis, fs.xlab,
ff.heading, ff.fixed, ff.random, ff.study,
ff.fixed.labels, ff.random.labels, ff.study.labels,
ff.hetstat, ff.axis, ff.xlab
- new arguments to change gap between columns
colgap.left, colgap.right=colgap,
colgap.forest, colgap.forest.left, colgap.forest.right
- new argument 'just' to change justification of text for
additional columns
- new argument 'addspace' to print a blank line at top and
bottom of study results
- argument 'squaresize' superseeds argument 'boxsize'
- new argument 'new' indicating whether a new figure should
be printed in an existing graphics window
(internally, the grid.newpage command is used if new=TRUE)
- no line is printed for the fixed effect and random effects
model if lty.fixed=NULL or lty.random=NULL, respectively
- symmetric forest plots can be produced by setting
argument xlim="s"
Function print.summary.meta:
- new argument print.CMH indicating whether Cochran-Mantel-Haenszel
test for overall effect should be printed (default print.CMH=FALSE)
- For subgroup analyses (i.e. groups defined by argument 'byvar'),
result for test of heterogeneity printed separately for fixed effect
and random effects model
Functions metabin and summary.meta:
- new argument print.CMH indicating whether Cochran-Mantel-Haenszel
test for overall effect should be printed (default print.CMH=FALSE)
The following help pages have been updated:
- forest.meta, metabin, print.summary.meta, summary.meta
2010-05-07, version 1.5-0
Version jump to 1.5-0 as several changes have been implemented.
New functions:
- metacor (meta-analysis of correlations)
- forest (generic method for forest plots)
- forest.meta (generic method for forest plots)
- radial (generic method for radial plots)
- radial.default (generic method for radial plots)
- radial.meta (generic method for radial plots)
- asin2p (function used internally)
- logit2p (function used internally)
- xlab (function used internally)
- z2cor (function used internally)
Functions forest.meta:
- new arguments (pooled.totals, pooled.events) to specify whether
total number of observations and events should be displayed in the plot
- new argument (pscale) to rescale proportions for objects of class metaprop
- modified so that argument label is recognised for other
effect measures than RR, OR, and HR
- modified so that argument xlim is recognised for other
effect measures than RR, OR, and HR
- arguments rightlabs and leftlabs accept NAs for columns
using default labels
- modified so that significant digits are printed uniformly
- correct sum of percentage weight is printed for random effects model
in forest plots with subgroups
- x limits (min,max) of the plot are defined by the width of
confidence intervals instead of (0,1) for objects of class metaprop
Function metaprop:
- implementation of additional transformations:
log transformation, logit transformation, raw, i.e. untransformed, proportions
- new argument sm to choose summary measure (i.e. transformation)
- use of argument freeman.tukey is deprecated (use argument sm instead)
Functions funnel and funnel.meta:
- argument y removed
Functions labbe and labbe.meta:
- argument y removed
Functions trimfill and trimfill.meta:
- argument seTE removed
Function summary.meta:
- new list objects H.w, I2.w, Q.b.fixed and Q.b.random
for heterogeneity statistics within subgroups
Extension for meta-analysis of correlations:
- forest.meta, metacum, metainf, print.meta,
print.summary.meta, summary.meta
Function plot.meta:
- a warning is printed that the function is no longer maintained
(function forest.meta should be used instead)
New list element version with information on version number of
meta package used to create an object (applies only to object
creating functions, e.g. metabin, metabias).
Update of several help pages.
Use file NEWS instead of ChangeLog to document changes.
2010-01-12, version 1.1-8
Functions summary.meta, print.summary.meta:
- modified so that a test for subgroup differences
is not calculated and printed for meta-analyses
using the Mantel-Haenszel method for binary data
2010-01-11, version 1.1-7
Functions metabin, metacont, metagen, metaprop:
- modified so that a sensible default value is used for argument bylab
if argument byvar is not missing
2010-01-11, version 1.1-6
Function forest:
- modified so that additional columns are printed in the correct order
if argument sort or order is used
2009-12-21, version 1.1-5
Function forest (incl. help page):
- new argument digits specifying minimal number of significant digits
for treatment estimate and its confidence interval
2009-11-04, version 1.1-4
Function summary.meta:
- modified so that results for subgroups (if byvar != NULL)
are calculated for both fixed effect and random effects model:
* list 'within' no longer returned by function summary.meta
* lists 'within.fixed' and 'within.random' returned by
function summary.meta
- modified so that variable name of subgroups is printed
correctly
- check whether input is an object of class summary.meta
Function print.summary.meta:
- modified so that a warning is printed if both comb.fixed and
comb.random are TRUE and results for subgroups are supposed to
be printed
Help pages of functions print.summary.meta and forest updated:
- detailed information on printing and plotting of subgroup
results if both comb.fixed and comb.random are TRUE
Help page of function metagen updated:
- new example with meta-analysis of survival data
2009-10-30, version 1.1-3
New functions trimfill, trimfill.default and trimfill.meta:
- generic method for trim-and-fill method
2009-10-09, version 1.1-2
New functions labbe, labbe.default, labbe.metabin:
- produce L'Abbe plots
New functions funnel, funnel.default and funnel.meta:
- generic method for funnel plots
Functions funnel.default and funnel.meta:
- modified so that contour-enhanced funnel plots can be produced
(new arguments: contour.levels, col.contour, ref)
- modified so that study labels can be printed on funnel plot
(new arguments: studlab, cex.studlab)
- modified so that line type, width and colour can be changed for
fixed effect treatment effect
(new arguments: lty.fixed, lwd.fixed, col.fixed)
- modified so that random effects treatment effect can be plotted
(new arguments: comb.random, lty.random, lwd.random, col.random)
- new default values for arguments:
* pch=21 (previously: pch=1)
* comb.fixed=x$comb.fixed
- modified so that background colour of points in funnel plot can
be changed
(new argument: bg)
Function forest:
- new default values for arguments lab.e and lab.c: x$label.e and
x$label.c, respectively. If these values are NULL the old default
values "Experimental" and "Control" are used.
Functions metabin, metacont, metagen:
- arguments label.e and label.c added
Function metacr:
- use arguments label.e and label.c in calls to functions
metabin, metacont, metagen
2009-08-31, version 1.0-6
First major version released on CRAN
No NEWS available for versions < 1.0